Related papers: ARbis Pictus: A Study of Language Learning with Au…
Speech is a rich signal, and labeled audio-text pairs are costly, making self-supervised learning essential for scalable representation learning. A core challenge in speech SSL is generating pseudo-labels that are both informative and…
Controlling artificial agents from visual sensory data is an arduous task. Reinforcement learning (RL) algorithms can succeed but require large amounts of interactions between the agent and the environment. To alleviate the issue,…
User Simulators are one of the major tools that enable offline training of task-oriented dialogue systems. For this task the Agenda-Based User Simulator (ABUS) is often used. The ABUS is based on hand-crafted rules and its output is in…
This paper addresses the unrealistic aspect of the commonly adopted Continuous Incremental Semantic Segmentation (CISS) scenario, termed overlapped. We point out that overlapped allows the same image to reappear in future tasks with…
We present an approach to evaluate the efficacy of annotations in augmenting learning environments in the context of Virtual Reality. Our study extends previous work highlighting the benefits of learning based in virtual reality and…
Pre-trained Vision Language Models (VLMs) have demonstrated notable progress in various zero-shot tasks, such as classification and retrieval. Despite their performance, because improving performance on new tasks requires task-specific…
Labeling data can be an expensive task as it is usually performed manually by domain experts. This is cumbersome for deep learning, as it is dependent on large labeled datasets. Active learning (AL) is a paradigm that aims to reduce…
In the world of big data, large but costly to label datasets dominate many fields. Active learning, a semi-supervised alternative to the standard PAC-learning model, was introduced to explore whether adaptive labeling could learn concepts…
Quality control is a crucial activity performed by manufacturing enterprises to ensure that their products meet quality standards and avoid potential damage to the brand's reputation. The decreased cost of sensors and connectivity enabled…
Most meta-learning methods assume that the (very small) context set used to establish a new task at test time is passively provided. In some settings, however, it is feasible to actively select which points to label; the potential gain from…
Tool-augmented language models, equipped with retrieval, memory, or external APIs, are reshaping AI, yet their theoretical advantages remain underexplored. In this paper, we address this question by demonstrating the benefits of in-tool…
This study presents the development of a marker-based augmented reality (AR) application designed to visualize the content of Surah al-Fil as an interactive and context-rich medium for Islamic education. Using a research and development…
Augmented reality (AR) has great potential for use in healthcare applications, especially remote medical training and supervision. In this paper, we analyze the usage of an AR communication system to teach a medical procedure, the placement…
Self-supervised learning, which learns by constructing artificial labels given only the input signals, has recently gained considerable attention for learning representations with unlabeled datasets, i.e., learning without any…
Learning from human feedback has gained traction in fields like robotics and natural language processing in recent years. While prior works mostly rely on human feedback in the form of comparisons, language is a preferable modality that…
Offline reinforcement learning can enable policy learning from pre-collected, sub-optimal datasets without online interactions. This makes it ideal for real-world robots and safety-critical scenarios, where collecting online data or expert…
Augmenting data in image space (eg. flipping, cropping etc) and activation space (eg. dropout) are being widely used to regularise deep neural networks and have been successfully applied on several computer vision tasks. Unlike previous…
Acoustical mismatch among training and testing phases degrades outstandingly speech recognition results. This problem has limited the development of real-world nonspecific applications, as testing conditions are highly variant or even…
Active learning as a paradigm in deep learning is especially important in applications involving intricate perception tasks such as object detection where labels are difficult and expensive to acquire. Development of active learning methods…
Deaf and hard-of-hearing (DHH) students face significant challenges in specialized educational settings, such as limited exposure to written and spoken language, a lack of tailored educational tools, and restricted access to resources,…